Reducing data access latency in SDSM systems using runtime optimizations

Authors:
Javier Bueno;Xavier Martorell;Juan José Costa;Toni Cortés;Eduard Ayguadé;Guansong Zhang;Christopher Barton;Raul Silvera
Affiliations:
Universitat Politècnica de Catalunya, Barcelona, Spain;Universitat Politècnica de Catalunya, Barcelona, Spain;Universitat Politècnica de Catalunya, Barcelona, Spain;Universitat Politècnica de Catalunya, Barcelona, Spain;Universitat Politècnica de Catalunya, Barcelona, Spain;IBM Toronto Lab, Markham, ON, Canada;IBM Toronto Lab, Markham, ON, Canada;IBM Toronto Lab, Markham, ON, Canada
Venue:
Proceedings of the 2010 Conference of the Center for Advanced Studies on Collaborative Research
Year:
2010

Citing 8
Cited 0

TreadMarks: Shared Memory Computing on Networks of Workstations

Computer
OpenMP for networks of SMPs

Journal of Parallel and Distributed Computing
JIAJIA: A Software DSM System Based on a New Cache Coherence Protocol

HPCN Europe '99 Proceedings of the 7th International Conference on High-Performance Computing and Networking
A Library Implementation of the Nano-Threads Programming Model

Euro-Par '96 Proceedings of the Second International Euro-Par Conference on Parallel Processing-Volume II
ParADE: An OpenMP Programming Environment for SMP Cluster Systems

Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Running OpenMP applications efficiently on an everything-shared SDSM

Journal of Parallel and Distributed Computing - Special issue: 18th International parallel and distributed processing symposium
Brazos: a third generation DSM system

NT'97 Proceedings of the USENIX Windows NT Workshop on The USENIX Windows NT Workshop 1997
Experiences using OpenMP based on compiler directed software DSM on a PC cluster

WOMPAT'03 Proceedings of the OpenMP applications and tools 2003 international conference on OpenMP shared memory parallel programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

Software Distributed Shared Memory (SDSM) systems offer a convenient way to run applications developed for shared memory systems on distributed systems with no changes to them. However, since SDSM systems add an extra layer of abstraction to the memory hierarchy, applications may suffer performance problems when running on top of them. Our main research interest is to develop a set of compiler and runtime system techniques that widen the range of applications that can efficiently run on SDSM systems. Currently we are targeting OpenMP applications due to the ease of use this programming model provides. In this paper we show the performance of a set of regular applications that perform well on our SDSM system. They were adapted from OpenCL codes provided by ATI, and re-written in OpenMP. When trying to exploit more complex applications with different data access patterns, we find more difficulties from a DSM system. As an example, we show the performance evaluation of the NAS MG benchmark, and two techniques we have developed to improve its data locality. Our SDSM infrastructure is composed of NanosDSM, an everything-shared SDSM developed at the Technical University of Catalonia (UPC) and the Barcelona Supercomputing Center (BSC), and the IBM XL SMP Runtime to allow the execution of the OpenMP applications.